EP3727159B1 - Echo window artifact classification and visual indicators for an ultrasound system - Google Patents

Echo window artifact classification and visual indicators for an ultrasound system Download PDF

Info

Publication number
EP3727159B1
EP3727159B1 EP18822243.4A EP18822243A EP3727159B1 EP 3727159 B1 EP3727159 B1 EP 3727159B1 EP 18822243 A EP18822243 A EP 18822243A EP 3727159 B1 EP3727159 B1 EP 3727159B1
Authority
EP
European Patent Office
Prior art keywords
artifact
artifacts
ultrasound
areas
image
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
EP18822243.4A
Other languages
German (de)
English (en)
French (fr)
Other versions
EP3727159A1 (en
EP3727159C0 (en
Inventor
Fuxing Yang
Joon Hwan Choi
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Verathon Inc
Original Assignee
Verathon Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Verathon Inc filed Critical Verathon Inc
Publication of EP3727159A1 publication Critical patent/EP3727159A1/en
Application granted granted Critical
Publication of EP3727159C0 publication Critical patent/EP3727159C0/en
Publication of EP3727159B1 publication Critical patent/EP3727159B1/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/5269—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving detection or reduction of artifacts
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/5215—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data
    • A61B8/5223—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data for extracting a diagnostic or physiological parameter from medical diagnostic data
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
    • A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/08—Detecting organic movements or changes, e.g. tumours, cysts, swellings
    • A61B8/0833—Detecting organic movements or changes, e.g. tumours, cysts, swellings involving detecting or locating foreign bodies or organic structures
    • A61B8/085—Detecting organic movements or changes, e.g. tumours, cysts, swellings involving detecting or locating foreign bodies or organic structures for locating body or organic structures, e.g. tumours, calculi, blood vessels, nodules
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/13—Tomography
    • A61B8/14—Echo-tomography
    • A61B8/145—Echo-tomography characterised by scanning multiple planes
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/46—Ultrasonic, sonic or infrasonic diagnostic devices with special arrangements for interfacing with the operator or the patient
    • A61B8/461—Displaying means of special interest
    • A61B8/463—Displaying means of special interest characterised by displaying multiple images or images and diagnostic data on one display
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/5292—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves using additional data, e.g. patient information, image labeling, acquisition parameters
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/2431—Multiple classes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/43—Detecting, measuring or recording for evaluating the reproductive systems
    • A61B5/4306—Detecting, measuring or recording for evaluating the reproductive systems for evaluating the female reproductive systems, e.g. gynaecological evaluations
    • A61B5/4318—Evaluation of the lower reproductive system
    • A61B5/4325—Evaluation of the lower reproductive system of the uterine cavities, e.g. uterus, fallopian tubes, ovaries
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/43—Detecting, measuring or recording for evaluating the reproductive systems
    • A61B5/4375—Detecting, measuring or recording for evaluating the reproductive systems for evaluating the male reproductive system
    • A61B5/4381—Prostate evaluation or disorder diagnosis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10132—Ultrasound image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30168—Image quality inspection

Definitions

  • Ultrasound scanners are typically used to identify a target organ or another structure in the body and/or determine features associated with the target organ/structure, such as the size of a structure or the volume of fluid in an organ. Obtaining an adequate quality of ultrasound images can be challenging even for experienced operators.
  • Implementations described herein utilize machine learning to classify artifact information from B-mode ultrasound echoes into simple visual indications within an ultrasound imaging system, to assist in providing better aiming and more accurate quantitative analysis.
  • a convolutional neural network can be used to generate a probability map corresponding to the shadows from different sources inside B-mode images.
  • Simple visual indications can then be constructed from the maps for the operator to make adjustments in order to achieve better image quality and better measurement accuracy.
  • a method for providing artifact detection and visualization during ultrasound image collection may be performed by a processor in an ultrasound system.
  • the method may include receiving ultrasound image data from an ultrasound probe, detecting areas with artifacts in the ultrasound image data, classifying the areas with artifacts into a class selected from a group of available artifact classes, generating an indication of the areas with an artifact for an ultrasound-based image, wherein the indications include a designation of the selected class, and presenting to an operator the ultrasound-based image and the indication of the areas with artifacts.
  • an ultrasound-based image may generally include a B-mode image, a C-mode image, or another type of image derived from ultrasound data.
  • Fig. 1 is a schematic of a scanning system 100 in which systems and methods described herein may be implemented.
  • scanning system 100 includes a probe 110, a base unit 120, and a cable 130.
  • Probe 110 includes a handle portion, a trigger, and a nose (or dome) portion. Medical personnel may hold probe 110 via the handle and press trigger 112 to activate one or more ultrasound transceivers, located in the nose portion, to transmit ultrasound signals toward a target object of interest, which may include an organ (e.g., a bladder, an aorta, a kidney, etc.) or a non-organ structure (e.g., a catheter, a needle, or another medical device).
  • a target object of interest which may include an organ (e.g., a bladder, an aorta, a kidney, etc.) or a non-organ structure (e.g., a catheter, a needle, or another medical device).
  • a target object of interest which may include an organ (e.g., a bladder, an aorta, a kidney, etc.) or a non-organ structure (e.g., a catheter, a needle, or another medical device).
  • probe 110 is located on pelvi
  • the dome of probe 110 is typically formed of a material that provides an appropriate acoustical impedance match to an anatomical portion and/or permits ultrasound energy to be properly focused as it is projected into the anatomical portion.
  • a material that provides an appropriate acoustical impedance match to an anatomical portion and/or permits ultrasound energy to be properly focused as it is projected into the anatomical portion For example, an acoustic gel or gel pads, illustrated at area 154 in Fig. 1 , may be applied to patient's skin over the region of interest (ROI) to provide an acoustical impedance match when the dome is placed against the skin.
  • ROI region of interest
  • Probe 110 includes one or more ultrasound transceiver elements and one or more transducer elements within the dome that transmit ultrasound energy outwardly from the dome, and receive acoustic reflections or echoes generated by internal structures/tissue within the anatomical portion.
  • the one or more ultrasound transducer elements may include a one-dimensional, or a two-dimensional array of piezoelectric elements that may be moved within the dome by a motor to provide different scan directions with respect to the transmission of ultrasound signals by the transceiver elements.
  • the transducer elements may be stationary with respect to probe 110 so that the selected anatomical region may be scanned by selectively energizing the elements in the array.
  • Probe 110 may communicate with base unit 120 via a wired connection, such as via cable 130. In other implementations, probe 110 may communicate with base unit 120 via a wireless connection (e.g., Bluetooth, Wi-Fi, etc.).
  • base unit 120 includes a display 122 to allow an operator to view processed results from an ultrasound scan, and/or to allow operational interaction with respect to the operator during operation of probe 110.
  • display 122 may include an output display/screen, such as a liquid crystal display (LCD), light emitting diode (LED) based display, or other type of display that provides text and/or image data to an operator.
  • display 122 may provide artifact visualizations overlaid on B-mode images to help determine the quality/accuracy of an ultrasound scan. Display 122 may also display two-dimensional or three-dimensional images of the selected anatomical region.
  • the dome of probe 110 may be positioned against a surface portion of patient 150 as illustrated in Fig. 1 that is proximate to the anatomical portion to be scanned.
  • the operator actuates the transceiver and transducer elements, causing the transceiver to transmit ultrasound signals into the body and receive corresponding return echo signals that may be at least partially processed by the transceiver to generate an ultrasound image of the selected anatomical portion.
  • the transceiver transmits ultrasound signals with the center frequency in a range that extends from approximately about two megahertz (MHz) to approximately 10 MHz or more.
  • probe 110 may be coupled to a base unit 120 that is configured to generate ultrasound energy at a predetermined frequency and/or pulse repetition rate and to transfer the ultrasound energy to the transceiver.
  • Base unit 120 also includes one or more processors or processing logic configured to process reflected ultrasound energy that is received by the transceiver to produce an image of the scanned anatomical region.
  • probe 110 may be a self-contained device that includes one or more microprocessors or processing logic configured within the probe 110 and software associated with the microprocessor to operably control the transceiver and transducer elements, and to process the reflected ultrasound energy to generate the ultrasound image. Accordingly, a display on probe 110 may be used to display the generated image and/or to view artifact visualizations and other information associated with the operation of the transceiver.
  • the transceiver may be coupled to a generalpurpose computer, such as a laptop or a desktop computer that includes software that at least partially controls the operation of the transceiver and transducer elements, and also includes software to process information transferred from the transceiver so that an image of the scanned anatomical region may be generated.
  • a generalpurpose computer such as a laptop or a desktop computer that includes software that at least partially controls the operation of the transceiver and transducer elements, and also includes software to process information transferred from the transceiver so that an image of the scanned anatomical region may be generated.
  • Fig. 2 is a block diagram of functional logic components implemented in system 100 in accordance with an exemplary implementation.
  • system 100 includes a data acquisition unit 210, an artifact identification unit 220, a visual indication generator 230, and main processing logic 240.
  • data acquisition unit 210 may be part of probe 110 and the other functional units (e.g., artifact identification unit 220, visual indication generator 230, and main processing logic 240) may be implemented in base unit 120.
  • data acquisition unit 210, artifact identification unit 220, visual indication generator 230, and main processing logic 240 may be implemented in probe 110.
  • probe 110 may transmit echo data and/or image data to a processing system via, for example, a wireless connection (e.g., Wi-Fi or some other wireless protocol/technology) that is located remotely from probe 110 and base unit 120.
  • a wireless connection e.g., Wi-Fi or some other wireless protocol/technology
  • probe 110 may include a transceiver that produces ultrasound signals, receives echoes from the transmitted signals and generates image data based on the received echoes.
  • Data acquisition unit 210 may include, for example, demodulation, decimation, log compression, and filtering sub-modules, to generate an image that can be presented for visualization by a human.
  • a rotating transducer or transducer array with probe 110 may scan along multiple scan planes.
  • Figs. 3A and 3B provide simplified illustrations of scan planes 310 (e.g., planes 310-1, 310-2, and 310-3) and 315 (e.g., planes 315-1, 315-2, 315-3, etc.) which may be employed by probe 110 to capture ultrasound images.
  • Data acquisition unit 210 may use image data from one or more scan planes 310 or 315 to generate two-dimensional B-mode images, such as B-mode images 410 and 420 shown in Figs. 4A and 4B , respectively. While three scan planes 310 and ten scan planes 315 are shown in Figs. 3A and 3B , respectively, in practice, more scan planes are used to compile a comprehensive image of a target object. For example, dozens of scan planes may be used by some probes 110.
  • data acquisition unit 210 obtains data associated with multiple scan planes corresponding to the region of interest in patient 150.
  • C-mode images may generally include a representation oriented perpendicular to typical B-mode scan planes 310, for example.
  • a C-mode image may include a crosssectional image generated from ultrasound data of scan planes 310 or 315 at a particular depth, as indicated by plane 320-1.
  • data acquisition unit 210 may use image data from a certain depth in each of scan planes 310 or 315 to generate a C-mode image.
  • a C-mode image may include a 'shadowgram' or 'projection' of 3D ultrasound data onto an 'XY' plane, where Z axis represents depth, as indicated by plane 320-2.
  • C-mode images may be presented as an ultrasound image or as a cartoon-like graphic. Simplified illustrations of C-mode images 510 and 520 are shown in Figs. 5A and 5B , respectively.
  • artifact identification unit 220 may perform pre-processing of an image and detect in real time if ultrasound artifacts (e.g., false-positive echoes or false-negative echoes due to shadows, air/poor coupling, bowel gases, and other types of interference) are present in an echo window, which may be a B-mode image, a C-mode image, or another type of ultrasound image.
  • artifact identification unit 220 may receive an input image from data acquisition unit 210 (e.g., any of images 410, 420, 510, 520, etc.) and detect features in the echo window that are indicative of ultrasound artifacts.
  • artifact identification unit 220 may analyze B-mode image data, C-mode image data, or other types of image data using a multi-class artifact categorization algorithm to recognize one or more types of artifacts, such as shadows, gases, air-interfaces, etc.
  • artifact identification unit 220 may detect an air scan area 412 and a pubic bone shadow 414 within B-mode image 410 that targets a bladder 416.
  • artifact identification unit 220 may detect an area of bowel gas 422 within B-mode image 420 that targets an aorta 424.
  • C-mode images are generated from a compilation of B-mode images.
  • Artifact identification unit 220 may similarly detect an air scan area 512 and a pubic bone shadow 514 within a C-mode image 510 that targets a bladder 516 (although air scan area 512 and pubic bone shadow 514 may not typically be shown in a conventional C-mode image). Referring to Fig. 5B , artifact identification unit 220 may detect areas of bowel gas 522 and an air scan area 524 within a C-mode image 520 that targets an aorta 526.
  • artifacts such as air scan area 412, pubic bone shadow 414, bowel gas 422, etc.
  • automatic real-time detection and visualization (or visual enhancement) of artifacts may simplify aiming of probe 110 and ensure better accuracy for both experienced and inexperienced operators. Detection and elimination of these artifacts in B-made images may also provide for more accurate C-mode images.
  • Artifact identification unit 220 is described further, for example, in connection with Fig. 9 .
  • visual indication generator 230 applies a visual indication, such as an overlay on images, for artifacts detected by artifact identification unit 220. For example, based on a type of artifact detected by artifact identification unit 220, visual indication generator 230 may provide a highlight or outline of an artifact area.
  • Figs. 6A-7B provide examples of sample outputs that may be generated by visual indication generator 230.
  • Figs. 6A and 6B illustrate visualizations applied to B-mode images 410 and 420, respectively.
  • Figs. 7A and 7B illustrate visualizations applied to C-mode images 510 and 520 respectively.
  • visual indication generator 230 may provide an output 610 for a bladder scan.
  • Output 610 may include B-mode image 410, an air artifact identifier 612, a shadow artifact identifier 614, and an organ outline 616.
  • B-mode image 410 may correspond to echo data from one of scan planes 310 or 315 of Figs. 3A or 3B .
  • Air artifact identifier 612 may be an outline, contrasting area, or another visible indicator highlighting air scan area 412 (e.g., as detected by artifact identification unit 220).
  • Shadow artifact identifier 614 may be another outline, contrasting area, or different visible indicator highlighting pubic bone shadow 414.
  • Organ outline 616 may correspond to an estimated shape of bladder 416 and may include another outline or visible indicator.
  • air artifact identifier 612 and shadow artifact identifier 614 may be color-coded to indicate a respective type of artifact (e.g., air and shadow).
  • artifact identifiers may be supplemented with visible or audible text instructions to an operator. For example, a separate legend explaining the colors or artifact markings may accompany output 610.
  • the echo window for B-mode image 410 is partially blocked by the pubic bone (e.g., due to improper aim) and air (e.g., due to poor coupling).
  • Bladder 416 in particular, is partially occluded by the pubic bone shadow 414, which means the estimated shape of bladder 416, as indicated by organ outline 616, may be inaccurate.
  • Indicators 612, 614, and 616 of output 610 provide a clear visual indication of how artifacts (e.g., air scan area 412 and pubic bone shadow 414) can impact a desired target (e.g., bladder 416) measurement without complex processing heuristics or delays.
  • indicators 612, 614, and 616 may provide an operator with real-time information that probe 110 adjustments are needed to obtain an accurate bladder scan.
  • visual indication generator 230 may provide an output 620 for an aorta scan.
  • Output 620 may include B-mode image 420, a gas artifact identifier 622, and an organ outline 624.
  • B-mode image 420 may correspond to echo data from one of scan planes 310 of Fig. 3A or scan planes 315 of Fig. 3B .
  • Gas artifact identifier 622 may be an outline, contrasting area, or another visible indicator highlighting bowel gas area 422 (e.g., as detected by artifact identification unit 220).
  • Organ outline 624 may correspond to an estimated shape of aorta 424 and may include another outline or indicator. Similar to artifact identifiers 612 and 614 described above, gas artifact identifier 622 may be color-coded and/or supplemented with descriptive text.
  • the echo window for B-mode image 420 is partially blocked by bowel gases. Aorta 424, however, is fully visible without obstruction.
  • Indicators 622 and 624 of output 620 provide a clear visual indication that artifacts (e.g., bowel gas area 422) do not impact the desired target (e.g., aorta 424) measurement without the need for complex processing heuristics or delays.
  • indicators 622 and 624 may provide an operator with real-time information that probe 110 adjustments are not needed to obtain an accurate scan.
  • visual indication generator 230 may provide an output 710 for a bladder scan.
  • Output 710 may include C-mode image 510, an air artifact identifier 712, a shadow artifact identifier 714, and an organ outline 716.
  • C-mode image 510 may correspond to echo data from C-mode image plane 320 of Fig. 3C .
  • Air artifact identifier 712 may be an outline, contrasting color, or another visible indicator highlighting air scan area 512 (e.g., as detected by artifact identification unit 220).
  • Shadow artifact identifier 714 may be another outline, contrasting color, or different visible indicator highlighting pubic bone shadow 514.
  • Organ outline 716 may correspond to an estimated shape of bladder 516 and may include another outline, color, or indicator.
  • air artifact identifier 712 and shadow artifact identifier 714 may be color-coded to indicate a respective type of artifact (e.g., air, shadow, etc.).
  • artifact identifiers may be supplemented with visible or audible text instructions to an operator.
  • the echo window for C-mode image 510 in general, and target bladder 516 in particular is partially blocked by the pubic bone shadow (e.g., due to improper aim) and air (e.g., due to poor probe-skin coupling).
  • Indicators 712, 714, and 716 of output 710 provide a clear visual indication of how the artifacts impede the desired target measurement (e.g., volume or size measurements of the bladder).
  • indicators 712, 714, and 716 may provide an operator with real-time information that probe 110 adjustments are needed to obtain an accurate bladder scan.
  • visual indication generator 230 may provide an output 720 for an aorta scan.
  • Output 720 may include C-mode image 520, gas artifact identifiers 722, air artifact identifier 724, and an organ outline 726.
  • C-mode image 510 may correspond to echo data from C-mode image plane 320 of Fig. 3C .
  • Gas artifact identifier 722 may be an outline, contrasting area, or another visible indicator highlighting bowel gas area 522 (e.g., as detected by artifact identification unit 220).
  • Air artifact identifier 724 may be an outline, contrasting color, or another visible indicator highlighting air scan area 524 (e.g., as detected by artifact identification unit 220).
  • Organ outline 726 may correspond to an estimated shape of aorta 526 and may include another outline or indicator. Similar to the other artifact identifiers described above, gas artifact identifier 722 may be color-coded and/or supplemented with descriptive text (e.g., "A” for air, “G” for gas, “S” for shadow, the words “air,” “gas,” shadow,” etc.).
  • a portion of the echo window for C-mode image 520 is blocked by air scan and bowel gases. Aorta 526, however, is visible without obstruction.
  • Indicators 722, 724, and 726 of output 720 provide a clear visual indication that artifacts (e.g., bowel gas area 522 and air scan area 524) do not impact the desired target (e.g., aorta 526) measurement without the need for complex processing heuristics or associated delays.
  • indicators 722, 724 and 726 may provide an operator with real-time information that probe 110 adjustments are not needed to obtain an accurate scan.
  • Figs. 6A-7B provide examples of visual artifact indicators for B-mode and C-mode scans for a bladder and aorta.
  • visual indication generator 230 may provide an output with visual indicators for artifacts in other scan modes and/or for other target objects.
  • main processing logic 240 may provide additional analysis of a target object (e.g., bladder 416, aorta 424, etc.), such as cavity-type recognition, volume estimations, diameter or size estimations, or other clinically useful information with B-mode, C-mode, or other types of images acquired by data acquisition unit 210.
  • a target object e.g., bladder 416, aorta 424, etc.
  • main processing logic 240 may identify a cavity as a bladder, estimate a volume for the bladder, or identify a diameter of the aorta.
  • System 100 may include more or fewer logic units/devices than illustrated in Figs. 1 and 2 .
  • system 100 may include multiple data acquisition units 210 and multiple processing units that process the received data.
  • system 100 may include additional elements, such as communication interfaces (e.g., radio frequency transceivers) that transmit and receive information via external networks to aid in analyzing ultrasound signals to identify a target object of interest.
  • communication interfaces e.g., radio frequency transceivers
  • FIG. 1 and 2 is provided for simplicity.
  • system 100 may include more or fewer logic units/devices than illustrated in Figs. 1 and 2 .
  • system 100 may include multiple data acquisition units 210 and multiple processing units that process the received data.
  • system 100 may include additional elements, such as communication interfaces (e.g., radio frequency transceivers) that transmit and receive information via external networks to aid in analyzing ultrasound signals to identify a target object of interest.
  • communication interfaces e.g., radio frequency transceivers
  • Fig. 8 is a block diagram illustrating communications between functional logic components in scanning system 100.
  • B-mode images 810 e.g., from data acquisition unit 210) may be received by artifact identification unit 220, which may detect features of pixels and/or pixel grouping within each B-mode image 810 to permit artifact classification.
  • Artifact identification unit 220 may associate artifact portions (e.g. pixels) of the B-mode image 810 into one or more classes based on criteria from training data.
  • artifact identification unit 220 may apply a pre-trained deep convolutional neural network (DCNN).
  • DCNN deep convolutional neural network
  • a DCNN or other image classification algorithms may be wellsuited for application of hardwired circuitry, such as a field-programmable gate array (FPGA), an application specific integrated circuits (ASIC), etc., to provide rapid image classification.
  • FPGA field-programmable gate array
  • ASIC application specific integrated circuits
  • Each type of artifact may result in distinct types of pixel groupings within an ultrasound image that can be detected using probability matching.
  • artifact identification unit 220 may include a probability map corresponding to the different types of shadows (e.g., strong shadows from pubic bone versus lighter shadows from bowel gas) and other artifacts (reverberations due to poor probe-to-skin coupling) inside B-mode images.
  • artifact definitions may be generated off-line by a machine learning system and stored in artifact identification unit 220.
  • artifact identification unit 220 may include a dynamic learning capability, where actual processed images and user responses to visualizations (e.g., visualizations 612, 712, etc.) may be used improve artifact identification unit 220.
  • artifact identification unit 220 may use four different classes: shadow from public bone 820, shadow from bowel gas 822, artifacts from bad coupling 824, and artifacts from other sources 826.
  • Shadow from public bone 820, shadow from bowel gas 822, artifacts from bad coupling 824 may represent primary known artifact classes that are detectable from pixel groupings in B-mode images.
  • Artifacts from other sources 826 may include any unidentified artifact or other types of known artifacts not in the primary known artifact classes, such as a catheter or needle shadow class, a rib shadow class, or other classes which impact the scanning image quality and associated quantitative analysis accuracy.
  • artifacts from other sources 826 may be separated into multiple classes or sub-classes, such as separate groupings for catheter or needle shadow class, a rib shadow class, and an unknown class.
  • pixels may be classified under multiple classes.
  • Artifact identification unit 220 may support any number of categories for output, as long as the amount of ultrasound images in the training dataset supports each category. However, as the total number of categories grows, the classification distance (e.g., in terms of image feature space) between two categories could be potentially decreased, which could lead to difficulties for the correct classification and the confusion to human operators. In one implementation, artifact identification unit 220 may use no more than six categories.
  • artifact classes 820, 822, 824, and 826 shown in Fig. 8 may be appropriate for a particular ultrasound application, such as conducting a bladder scan.
  • different types or amounts of artifact classes may be used in artifact identification unit 220.
  • artifacts from bad coupling and shadow from bowel gas may be the primary classes with an undefined (or "other sources") class for other artifacts.
  • other sources or “other sources” class
  • shadows from ribs and shadows from medical devices may be two primary artifact classifications (e.g., instead of being grouped together in an "other sources” class).
  • Artifact identification unit 220 may forward locations and classes of classified pixels to visual indication generator 230.
  • Visual indication generator 230 produces overlays corresponding to the location and class of the artifact pixels.
  • a B-mode visualizations unit 830 may apply visualizations (e.g., air artifact identifier 612, gas artifact identifier 622, etc.) directly to B-mode images.
  • a C-mode visualizations unit 840 may receive and compile locations for B-mode visualizations with other B-mode data to generate C-mode visualizations (e.g., air artifact identifier 712, gas artifact identifier 722, etc.).
  • other visualizations unit 850 may receive and compile locations of B-mode visualizations with other image data to generate the other types of ultrasound images.
  • Fig. 9 is a block diagram of exemplary communications for generating real-time artifact visualizations in scanning system 100.
  • An operator 900 may use ultrasound probe 110 to acquire real-time data from a targeted anatomical region.
  • operator 900 may control probe 110 to position 905 the nose of probe 110 toward an organ of interest (e.g., organ 152 of Fig. 1 ) and emit ultrasonic signals.
  • organ of interest e.g., organ 152 of Fig. 1
  • Data acquisition unit 210 may receive echo data and process the echo data to generate, for example, a two-dimensional B-mode image 910. Data acquisition unit 210 may forward B-mode image 910 to artifact identification unit 220.
  • Artifact identification unit 220 may analyze image 910 using, for example, a multi-class artifact categorization algorithm to classify different areas (e.g., pixels) of image 910 with one or more of multiple different artifact categories, such as an air scan area 412, a pubic bone shadow 414, etc. According to an implementation, pixels of image 910 may be simultaneously included in two separate categories. For example, artifact identification unit 220 may identify some pixels in image 910 as having both strong shadows and reverberations. Artifact identification unit 220 may forward the category associations 915 for pixels of image 910 to visual indication generator 230.
  • a multi-class artifact categorization algorithm to classify different areas (e.g., pixels) of image 910 with one or more of multiple different artifact categories, such as an air scan area 412, a pubic bone shadow 414, etc.
  • pixels of image 910 may be simultaneously included in two separate categories.
  • artifact identification unit 220 may identify some pixels in image 910 as
  • Visual indication generator 230 may receive category associations 915 and generate artifact visualizations based on category associations 915. According to an implementation, visual indication generator 230 may match the category associations 915 to a particular color, indication, and/or textual reference using a table.
  • Visual indication generator 230 may select appropriate visualizations/text corresponding to the category for pixels in image 910 and submit an enhanced image 920 (e.g., output 610, 620, etc.) to display 122 for presentation to operator 900.
  • the artifact visualizations e.g., gas artifact identifier 622, etc.
  • artifact identification unit 220 analyzes individual B-mode images (e.g., two-dimensional images)
  • enhanced image 920 from visual indication generator 230 may be presented (via display 122) in real-time (e.g., less than 0.5 seconds delay).
  • Artifact visualizations for C-mode images, which are generated from the B-mode visualizations, may be similarly presented without significant delay.
  • Operator 900 may detect 925 enhanced image 920 from display 122. Assuming enhanced image 920 includes artifact visualizations that require a user to adjust probe 110, operator 900 may re-position 905 probe 110 (or take other actions to correct artifacts). Data acquisition unit 210 may receive new echo data and process the new echo data to generate another B-mode image 910, C-mode image, etc. Artifact identification unit 220 may analyze the image 910 for artifact pixels to again provide category associations 915 to visual indication generator 230.
  • operator 900 may choose to not adjust probe 110.
  • Visual indication generator 230 may forward the unobstructed/accepted image 930 to main processing logic 240.
  • Main processing logic 240 may receive image 930 and subsequent images 930, if needed, to provide a desired measurement or calculation, such as an organ boundary, bladder volume estimate, cavity recognition, aorta size, etc., based on image 930. Main processing logic 240 may provide a calculated result 935 to display 122 for presentation to the operator 900.
  • a desired measurement or calculation such as an organ boundary, bladder volume estimate, cavity recognition, aorta size, etc.
  • Fig. 10 is a block diagram of exemplary communications for generating real-time artifact visualizations in scanning system 100 according to another implementation. Communications in Fig. 10 represent feedback provided to an operator along with a requested output.
  • operator 900 may control probe 110 to position 905 the nose of probe 110 toward an organ of interest and emit ultrasonic signals.
  • Data acquisition unit 210 may receive echo data and process the echo data to generate image 910.
  • Data acquisition unit 210 may send image 910 to artifact identification unit 220.
  • Artifact identification unit 220 may analyze image 910 and classify pixel groupings or areas within image 910 into one or more artifact categories.
  • Artifact identification unit 220 may provide category associations 915 for image 910 to visual indication generator 230.
  • data acquisition unit 210 may send image 910 to main processing logic 240.
  • Main processing logic 240 may receive image 910 and subsequent images 910, if needed, to detect a target object (e.g., a bladder, kidney, aorta, medical device, etc.) and provide a desired measurement or calculation, such as an organ boundary/shape or a bladder volume estimate, based on image 910.
  • a target object e.g., a bladder, kidney, aorta, medical device, etc.
  • a desired measurement or calculation such as an organ boundary/shape or a bladder volume estimate
  • Visual indication generator 230 may receive category associations 915 and calculated results 1010. Visual indication generator 230 may use category associations 915 and calculated results 1010 to generate a visualization of artifact areas for operator 900. In one implementation, visual indication generator 230 may provide the calculated result 1010 with additional guidance to indicate a potential error in a calculated result due to the presence of artifacts.
  • Visual indication generator 230 may select appropriate visualizations corresponding to the class of artifacts detected within image 910 and submit the images with artifact visualizations as output 1020 to display 122 for presentation to operator 900.
  • output 1020 may correspond to output 610, 620, 710, or 720, described above and may be presented via display 122.
  • Operator 900 may detect 1025 output 1020 on display 122. Operator 900 can choose to adjust probe 110 and re-scan or simply accept the result based on the location of the target object relative to the visualized artifacts (if any).
  • Fig. 11 is a flow diagram illustrating an exemplary process 1100 for generating real-time artifact visualizations for ultrasound scans.
  • Process 1100 may be performed, for example, by base unit 120 of system 100. In another implementation, process 1100 may be performed by base unit 120 in conjunction with probe 110. In one implementation, process 1100 may begin after probe 110 obtains an ultrasound image as described above.
  • Process 1100 may include receiving and processing scan images (block 1110).
  • data acquisition unit 210) may receive one or more B-mode ultrasound image from probe 110 and apply noise reduction and/or other pre-processing techniques to remove speckle and background noise from the image.
  • the aspect ratio of the raw B-mode image can be adjusted through a resizing process to compensate for differences between axial and lateral resolution.
  • a scan conversion can also be applied to make a bladder shape more accurately reflect the actual shape of a typical bladder.
  • Process 1100 may also include detecting ultrasound artifacts in the scan images (block 1120) and visualizing the detected artifact areas (block 1130).
  • artifact identification unit 220 may receive pre-processed images, such as image 910, from data acquisition unit 210.
  • Artifact identification unit 220 may analyze pixel groupings in image 910 using, for example, a multi-class image categorization algorithm to classify areas of image 910 into one or more of multiple different artifact categories (e.g., pubic bone shadow, bowel gas shadow, reverberations, etc.).
  • Visual indication generator 230 generates visible indicators for the different types of artifacts in real time and overlay the artifact visualizations over the scan image for presentation to the operator 900.
  • the operator may decide to accept the scan (block 1140). For example, based on the location of visualized artifacts relative to a target object, operator 900 may determine that a scan is acceptable despite the presence of ancillary artifacts. Alternatively, operator 900 may determine that artifacts (e.g., as represented by visualizations 612, 712, etc.) require probe adjustment and re-scanning.
  • artifacts e.g., as represented by visualizations 612, 712, etc.
  • process 1100 may include the operator adjusting the probe (block 1150) and returning to block 1110 to receive and process scan images.
  • operator 900 may reject a scan with output (e.g. output 610, 710) that shows artifacts occluding a target object.
  • Operator 900 may adjust the probe 110 position, apply more gel to the skin, or take other corrective actions to improve the scan result and initiate another scan.
  • process 1100 may include performing main processing (block 1160) and presenting a result (block 1170).
  • operator 900 may accept a scan with no artifacts or output (e.g. output 620, 720) that shows artifacts in the echo window do not impact view of a target object.
  • Main processing logic 240 may perform a request calculation/measurement for the target object and return a result (e.g., bladder volume, aorta diameter, etc.) to operator 900.
  • Fig. 11 shows a particular order of blocks for process 1110, in other implementations, process 1100 may be performed in a different order.
  • the main data processing of block 1160 may be performed simultaneously with blocks 1120 and/or 1130.
  • Fig. 12 is a diagram illustrating exemplary physical components of base unit 120.
  • Base unit 120 may include a bus 1210, a processor 1220, a memory 1230, an input component 1240, an output component 1250, and a communication interface 1260.
  • probe 110 may include similar components.
  • Bus 1210 may include a path that permits communication among the components of base unit 120.
  • Processor 1220 may include a processor, microprocessors, ASICs, controllers, programmable logic devices, chipsets, FPGAs, graphics processing unit (GPU), application specific instruction-set processors (ASIPs), system-on-chips (SoCs), central processing units (CPUs) (e.g., one or multiple cores), microcontrollers, and/or some other type of component that interprets and/or executes instructions and/or data.
  • Processor 1220 may be implemented as hardware (e.g., an FPGA, etc.), a combination of hardware and software (e.g., a SoC, an ASIC, etc.), may include one or multiple memories (e.g., cache, etc.), etc.
  • Memory 1230 may include any type of dynamic storage device that may store information and instructions (e.g., software 1235), for execution by processor 1220, and/or any type of non-volatile storage device that may store information for use by processor 1220.
  • Software 1235 includes an application or a program that provides a function and/or a process.
  • Software 1235 is also intended to include firmware, middleware, microcode, hardware description language (HDL), and/or other form of instruction.
  • HDL hardware description language
  • Input component 1240 may include a mechanism that permits an operator to input information to base unit 120, such as a keyboard, a keypad, a button, a switch, a touch screen, etc.
  • Output component 1250 may include a mechanism that outputs information to the operator, such as a display (e.g., display 122), a speaker, one or more light emitting diodes (LEDs), etc.
  • Communication interface 1260 may include a transceiver that enables base unit 120 to communicate with other devices and/or systems via wireless communications, wired communications, or a combination of wireless and wired communications.
  • communication interface 1260 may include mechanisms for communicating with another device or system, such as probe 110, via a network, or to other devices/systems, such as a system control computer that monitors operation of multiple base units (e.g., in a hospital or another type of medical monitoring facility).
  • communication interface 1260 may be a logical component that includes input and output ports, input and output systems, and/or other input and output components that facilitate the transmission of data to/from other devices.
  • Base unit 120 may perform certain operations in response to processor 1220 executing software instructions (e.g., software 1235) contained in a computer-readable medium, such as memory 1230.
  • a computer-readable medium may be defined as a non-transitory memory device.
  • a non-transitory memory device may include memory space within a single physical memory device or spread across multiple physical memory devices.
  • the software instructions may be read into memory 1230 from another computer-readable medium or from another device.
  • the software instructions contained in memory 1230 may cause processor 1220 to perform processes described herein.
  • hardwired circuitry such as an ASIC, an FPGA, etc., may be used in place of or in combination with software instructions to implement processes described herein.
  • implementations described herein are not limited to any specific combination of hardware circuitry and software.
  • Base unit 120 may include fewer components, additional components, different components, and/or differently arranged components than those illustrated in Fig. 12 .
  • base unit 120 may include one or more switch fabrics instead of, or in addition to, bus 1210. Additionally, or alternatively, one or more components of base unit 120 may perform one or more tasks described as being performed by one or more other components of base unit 120.
  • Systems and methods described herein provide real-time artifact visualizations to operators during the ultrasound scanning.
  • the real-time artifact visualization is helpful in assisting inexperienced operators, as well as experienced operators, to acquire high quality ultrasound data and achieve accurate calculated organ dimensions, such as bladder volume measurements, aorta diameter, etc.
  • Machine learning such as a deep convolutional neural network, enables rapid classification of artifact areas within scan images that can be used to provide real-time feedback.
  • Systems and methods described herein minimize the requirement for an operator to interpret artifacts within ultrasound images and transfer that task to logic within system 100.
  • Conventional ultrasound systems require that an operator interpret image content or wait for complete scan results to determine if artifacts have impacted the scan results.
  • correctly understanding what happens in an ultrasound image is not a trivial task.
  • the systems and methods described herein perform an initial level of artifact detection for the operators to minimize the burden of image interpretation and delays of a full scan calculation before detecting probe operator errors.

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Theoretical Computer Science (AREA)
  • Animal Behavior & Ethology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Surgery (AREA)
  • Veterinary Medicine (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Physiology (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Vascular Medicine (AREA)
  • Databases & Information Systems (AREA)
  • Fuzzy Systems (AREA)
  • Signal Processing (AREA)
  • Psychiatry (AREA)
  • Quality & Reliability (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
EP18822243.4A 2017-12-20 2018-12-07 Echo window artifact classification and visual indicators for an ultrasound system Active EP3727159B1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US201762608134P 2017-12-20 2017-12-20
PCT/US2018/064483 WO2019125790A1 (en) 2017-12-20 2018-12-07 Echo window artifact classification and visual indicators for an ultrasound system

Publications (3)

Publication Number Publication Date
EP3727159A1 EP3727159A1 (en) 2020-10-28
EP3727159C0 EP3727159C0 (en) 2024-02-28
EP3727159B1 true EP3727159B1 (en) 2024-02-28

Family

ID=64744992

Family Applications (1)

Application Number Title Priority Date Filing Date
EP18822243.4A Active EP3727159B1 (en) 2017-12-20 2018-12-07 Echo window artifact classification and visual indicators for an ultrasound system

Country Status (7)

Country Link
US (1) US11389139B2 (ja)
EP (1) EP3727159B1 (ja)
JP (1) JP7022217B2 (ja)
KR (1) KR102491757B1 (ja)
CN (1) CN111629670B (ja)
CA (1) CA3085619C (ja)
WO (1) WO2019125790A1 (ja)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102106694B1 (ko) * 2018-05-17 2020-05-04 한국과학기술원 뉴럴 네트워크를 이용하는 영상 처리 장치 및 상기 장치가 수행하는 방법
US12016729B2 (en) * 2020-01-24 2024-06-25 Canon Kabushiki Kaisha Ultrasonic diagnostic apparatus, learning apparatus, and image processing method
CN115297786A (zh) * 2020-03-24 2022-11-04 富士胶片株式会社 超声波诊断装置、超声波诊断装置的控制方法及超声波诊断装置用处理器
US11457896B2 (en) * 2020-09-23 2022-10-04 GE Precision Healthcare LLC Ultrasound imaging system and method for generating an enhanced image to enhance a shadow region
CN113689939B (zh) * 2021-10-26 2022-04-08 萱闱(北京)生物科技有限公司 用于图像特征匹配的图像存储方法、系统和计算设备
JP2023084862A (ja) 2021-12-08 2023-06-20 富士フイルム株式会社 超音波診断装置および超音波診断装置の制御方法
JP2023141907A (ja) 2022-03-24 2023-10-05 富士フイルム株式会社 超音波診断システムおよび超音波診断システムの制御方法
JP2023143418A (ja) * 2022-03-25 2023-10-06 富士フイルム株式会社 超音波診断装置とその作動方法

Family Cites Families (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4835712A (en) * 1986-04-14 1989-05-30 Pixar Methods and apparatus for imaging volume data with shading
US6398733B1 (en) 2000-04-24 2002-06-04 Acuson Corporation Medical ultrasonic imaging system with adaptive multi-dimensional back-end mapping
GB2391625A (en) * 2002-08-09 2004-02-11 Diagnostic Ultrasound Europ B Instantaneous ultrasonic echo measurement of bladder urine volume with a limited number of ultrasound beams
US7536044B2 (en) 2003-11-19 2009-05-19 Siemens Medical Solutions Usa, Inc. System and method for detecting and matching anatomical structures using appearance and shape
US7876934B2 (en) 2004-11-08 2011-01-25 Siemens Medical Solutions Usa, Inc. Method of database-guided segmentation of anatomical structures having complex appearances
US7648460B2 (en) * 2005-08-31 2010-01-19 Siemens Medical Solutions Usa, Inc. Medical diagnostic imaging optimization based on anatomy recognition
US7804990B2 (en) 2006-01-25 2010-09-28 Siemens Medical Solutions Usa, Inc. System and method for labeling and identifying lymph nodes in medical images
US7822252B2 (en) 2006-11-28 2010-10-26 Siemens Medical Solutions Usa, Inc. Method of multiple instance learning and classification with correlations in object detection
CA2688758C (en) 2007-05-16 2016-07-05 Verathon Inc. System and method for bladder detection using harmonic imaging
US9672471B2 (en) 2007-12-18 2017-06-06 Gearbox Llc Systems, devices, and methods for detecting occlusions in a biological subject including spectral learning
US8885926B2 (en) 2009-04-15 2014-11-11 Massachusetts Institute Of Technology Image and data segmentation
KR101221288B1 (ko) * 2010-04-26 2013-01-10 삼성메디슨 주식회사 적응적 클러터 필터링을 수행하는 초음파 시스템 및 방법
JP6219835B2 (ja) * 2011-10-28 2017-10-25 ディスィジョン サイエンシズ インターナショナル コーポレーション 超音波イメージングにおけるスペクトル拡散符号化波形
US9033887B2 (en) 2012-05-31 2015-05-19 Siemens Corporation Mitral valve detection for transthoracic echocardiography
JP6033701B2 (ja) * 2013-02-13 2016-11-30 ジーイー・メディカル・システムズ・グローバル・テクノロジー・カンパニー・エルエルシー 超音波診断装置及びその制御プログラム
WO2014155272A1 (en) * 2013-03-28 2014-10-02 Koninklijke Philips N.V. Real-time quality control for acquisition of 3d ultrasound images
US9700219B2 (en) 2013-10-17 2017-07-11 Siemens Healthcare Gmbh Method and system for machine learning based assessment of fractional flow reserve
US9918696B2 (en) 2014-01-30 2018-03-20 Koninklijke Philips N.V. Method and apparatus for detecting a gas pocket using ultrasound
KR20160020917A (ko) 2014-08-14 2016-02-24 삼성전자주식회사 컴퓨터 보조 진단 장치 및 방법
US10430688B2 (en) * 2015-05-27 2019-10-01 Siemens Medical Solutions Usa, Inc. Knowledge-based ultrasound image enhancement
WO2016194161A1 (ja) 2015-06-03 2016-12-08 株式会社日立製作所 超音波診断装置、及び画像処理方法
US11096671B2 (en) * 2015-09-10 2021-08-24 Siemens Medical Solutions Usa, Inc. Sparkle artifact detection in ultrasound color flow
US11832969B2 (en) * 2016-12-22 2023-12-05 The Johns Hopkins University Machine learning approach to beamforming
JP7005191B2 (ja) * 2017-06-30 2022-01-21 キヤノンメディカルシステムズ株式会社 画像処理装置、医用画像診断装置、及びプログラム

Also Published As

Publication number Publication date
US11389139B2 (en) 2022-07-19
EP3727159A1 (en) 2020-10-28
WO2019125790A1 (en) 2019-06-27
KR102491757B1 (ko) 2023-01-27
CN111629670A (zh) 2020-09-04
CN111629670B (zh) 2024-04-05
JP7022217B2 (ja) 2022-02-17
JP2021506470A (ja) 2021-02-22
EP3727159C0 (en) 2024-02-28
KR20200101418A (ko) 2020-08-27
CA3085619A1 (en) 2019-07-27
CA3085619C (en) 2023-07-04
US20190183462A1 (en) 2019-06-20

Similar Documents

Publication Publication Date Title
EP3727159B1 (en) Echo window artifact classification and visual indicators for an ultrasound system
US11464490B2 (en) Real-time feedback and semantic-rich guidance on quality ultrasound image acquisition
US8172753B2 (en) Systems and methods for visualization of an ultrasound probe relative to an object
RU2667617C2 (ru) Система и способ эластографических измерений
US10219782B2 (en) Position correlated ultrasonic imaging
EP3554380B1 (en) Target probe placement for lung ultrasound
US20110255762A1 (en) Method and system for determining a region of interest in ultrasound data
JP2012506283A (ja) ３次元超音波画像化
US11432803B2 (en) Method and system for generating a visualization plane from 3D ultrasound data
US11931201B2 (en) Device and method for obtaining anatomical measurements from an ultrasound image
US11278259B2 (en) Thrombus detection during scanning
US11766245B2 (en) Ultrasonic diagnostic apparatus and control method
JP6648587B2 (ja) 超音波診断装置
KR102578072B1 (ko) 초음파 진단 장치 및 그 제어 방법
US8636662B2 (en) Method and system for displaying system parameter information
CN115153634A (zh) 一种智能超声检查诊断方法及系统
CN114631841A (zh) 超声扫查反馈装置
US12121393B2 (en) Automated prostate analysis system
US20210312652A1 (en) Automated prostate analysis system
CN114680928A (zh) 超声扫查反馈系统

Legal Events

Date Code Title Description
STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: UNKNOWN

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE

PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE

17P Request for examination filed

Effective date: 20200610

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

AX Request for extension of the european patent

Extension state: BA ME

DAV Request for validation of the european patent (deleted)
DAX Request for extension of the european patent (deleted)
STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: EXAMINATION IS IN PROGRESS

17Q First examination report despatched

Effective date: 20230222

P01 Opt-out of the competence of the unified patent court (upc) registered

Effective date: 20230527

RIC1 Information provided on ipc code assigned before grant

Ipc: A61B 8/00 20060101ALI20230811BHEP

Ipc: A61B 5/00 20060101ALI20230811BHEP

Ipc: G06N 3/02 20060101ALI20230811BHEP

Ipc: G06T 7/00 20170101ALI20230811BHEP

Ipc: G16H 50/20 20180101ALI20230811BHEP

Ipc: G16H 30/40 20180101ALI20230811BHEP

Ipc: G06N 3/08 20060101ALI20230811BHEP

Ipc: G01S 7/52 20060101ALI20230811BHEP

Ipc: G06N 3/045 20230101ALI20230811BHEP

Ipc: G06T 5/00 20060101ALI20230811BHEP

Ipc: A61B 8/08 20060101AFI20230811BHEP

GRAP Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOSNIGR1

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: GRANT OF PATENT IS INTENDED

INTG Intention to grant announced

Effective date: 20230928

RAP3 Party data changed (applicant data changed or rights of an application transferred)

Owner name: VERATHON INC.

GRAS Grant fee paid

Free format text: ORIGINAL CODE: EPIDOSNIGR3

GRAA (expected) grant

Free format text: ORIGINAL CODE: 0009210

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE PATENT HAS BEEN GRANTED

AK Designated contracting states

Kind code of ref document: B1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

REG Reference to a national code

Ref country code: GB

Ref legal event code: FG4D

REG Reference to a national code

Ref country code: CH

Ref legal event code: EP

REG Reference to a national code

Ref country code: DE

Ref legal event code: R096

Ref document number: 602018065950

Country of ref document: DE

REG Reference to a national code

Ref country code: IE

Ref legal event code: FG4D

U01 Request for unitary effect filed

Effective date: 20240315

U07 Unitary effect registered

Designated state(s): AT BE BG DE DK EE FI FR IT LT LU LV MT NL PT SE SI

Effective date: 20240325

P04 Withdrawal of opt-out of the competence of the unified patent court (upc) registered

Effective date: 20240412

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: IS

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20240628

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: GR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20240529

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: HR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20240228

Ref country code: RS

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20240528

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: ES

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20240228

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: RS

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20240528

Ref country code: NO

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20240528

Ref country code: IS

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20240628

Ref country code: HR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20240228

Ref country code: GR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20240529

Ref country code: ES

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20240228

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: PL

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20240228

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: PL

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20240228

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: SM

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20240228